Python 运行Adam优化器
我尝试运行AdamOptimizer进行一步训练,但没有成功Python 运行Adam优化器,python,tensorflow,conv-neural-network,Python,Tensorflow,Conv Neural Network,我尝试运行AdamOptimizer进行一步训练,但没有成功 optimizer = tf.train.AdamOptimizer(learning_rate) init = tf.global_variables_initializer() with tf.Session() as sess: sess.run(init) sess.run(optimizer.minimize(cost), feed_dict={X:X_data, Y: Y_data}) 控制台发出一个看
optimizer = tf.train.AdamOptimizer(learning_rate)
init = tf.global_variables_initializer()
with tf.Session() as sess:
sess.run(init)
sess.run(optimizer.minimize(cost), feed_dict={X:X_data, Y: Y_data})
控制台发出一个看起来很难看的错误:
FailedPreconditionError (see above for traceback): Attempting to use uninitialized value beta1_power
[[Node: beta1_power/read = Identity[T=DT_FLOAT, _class=["loc:@W1"], _device="/job:localhost/replica:0/task:0/cpu:0"](beta1_power)]]
在代码中,成本是一个定义良好的函数,使用两个参数X、Y(分别输入NN和训练标签)实现conv NN和逻辑损耗函数
关于什么可能是错误的,有什么想法吗?优化器。最小化(成本)是在图形中创建新的值和变量
调用sess.run(init)
时,.minimize
方法创建的变量尚未定义:由此产生错误
您只需在调用tf.global\u variables\u initializer()之前声明最小化操作即可。
:
optimizer = tf.train.AdamOptimizer(learning_rate)
minimize = optimizer.minimize(cost)
init = tf.global_variables_initializer()
with tf.Session() as sess:
sess.run(init)
sess.run(minimize, feed_dict={X:X_data, Y: Y_data})